A decision-making exercise that expands a choice beyond two obvious alternatives. It looks for overlooked approaches, combinations, different uses of resources, and solutions used by others.

Use it when choosing a product direction, project approach, investment, or response to a problem and you need more possible paths.

It reduces narrow framing—the habit of treating a decision as only “yes or no” or as a choice between two options.

widen — Command for Claude Code by neurofoo/agent-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/neurofoo/agent-skills

Made for: Claude Code.

Or install thinking-frameworks, the plugin that ships this one along with the rest of its 8 skills, 8 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/neurofoo/agent-skills/widen/github.svg)](https://agentmods.dev/commands/neurofoo/agent-skills/widen)

Your own site

<a href="https://agentmods.dev/commands/neurofoo/agent-skills/widen"><img src="https://agentmods.dev/badge/commands/neurofoo/agent-skills/widen/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/neurofoo/agent-skills/widen"><img src="https://agentmods.dev/badge/commands/neurofoo/agent-skills/widen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 557 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00557
Opus 5.5	$0.00000	$0.00223
Sonnet 5.5	$0.00000	$0.00111
Haiku 4.5	$0.00000	$0.00056

Measured 1mo ago against content hash 4a0decad9c18, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

widen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

wrap/commands/widen.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Widen Your Options

Generate more options to escape narrow framing. Counter the tendency to see decisions as "whether or not" instead of "which of many."

Instructions

Take the current decision framing and expand it to include more options. Use specific techniques to discover overlooked alternatives.

Output Format

Current Decision: [How it's currently framed]

Narrow Framing Check

Is this a "whether or not" decision? [Yes/No] — If yes, that's a sign of narrow framing.

The two obvious options:

[Option that seems obvious]
[The other obvious option]

Option Expansion Techniques

Vanishing Options Test

"If both current options disappeared, what would you do?"

[New option 1]
[New option 2]

Opportunity Cost

"What else could you do with the same time, money, or effort?"

[Alternative use 1]
[Alternative use 2]

Find Someone Who Solved It

"Who has faced this problem before? What did they do?"

Person/Company	Their Solution	Applicable?
[who]	[what they did]	[yes/no/partial]

Multi-Tracking

"Can we do multiple options simultaneously instead of choosing one?"

[Combined approach 1]
[Combined approach 2]

AND vs OR

"Instead of A OR B, is there a way to get A AND B?"

[Possibility for having both]

The "Opposite" Option

"What if we did the exact opposite of what we're considering?"

[Opposite approach and what we can learn from it]

Expanded Option Set

#	Option	Type	Notes
1	[option]	Original	[note]
2	[option]	Original	[note]
3	[option]	Vanishing	[note]
4	[option]	Multi-track	[note]
5	[option]	Copied	[note]
6	[option]	AND/OR	[note]

Reframed Decision

Old frame: "Should we do X or Y?"

New frame: "Given we want [outcome], which of these [N] paths best achieves it?"

Guidelines

"Whether or not" is almost always too narrow
Great decisions come from great options
You can't choose a better option if you haven't imagined it
Look for the option you're afraid to consider

Read the full file on GitHub · 92 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 92 lines · 0 tokens per session scan A 4a0decad9c18

Subscribe to this mod's changes

widen is a command published in the GitHub repository neurofoo/agent-skills (122 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 557 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning

widen